Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 99 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.8759. Min Act: -0.1700

Data Index: 5210889 (Open Web Text)

Max Activating Token Index: 539

Text #1

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.8388. Min Act: -0.1700

Data Index: 4231084 (Open Web Text)

Max Activating Token Index: 646

Text #2

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.7729. Min Act: -0.1700

Data Index: 8684176 (Open Web Text)

Max Activating Token Index: 478

Text #3

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.7689. Min Act: -0.1700

Data Index: 3565775 (Open Web Text)

Max Activating Token Index: 630

Text #4

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.7980. Min Act: -0.1700

Data Index: 7272523 (Open Web Text)

Max Activating Token Index: 291

Text #5

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.7724. Min Act: -0.1700

Data Index: 7135550 (Open Web Text)

Max Activating Token Index: 460

Text #6

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.7911. Min Act: -0.1700

Data Index: 4291670 (Open Web Text)

Max Activating Token Index: 661

Text #7

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.7854. Min Act: -0.1700

Data Index: 6144787 (Open Web Text)

Max Activating Token Index: 543

Text #8

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.7885. Min Act: -0.1700

Data Index: 5820025 (Open Web Text)

Max Activating Token Index: 489

Text #9

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.7758. Min Act: -0.1700

Data Index: 7560102 (Open Web Text)

Max Activating Token Index: 896

Text #10

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.7903. Min Act: -0.1700

Data Index: 4908762 (Open Web Text)

Max Activating Token Index: 211

Text #11

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.7836. Min Act: -0.1700

Data Index: 6769057 (Open Web Text)

Max Activating Token Index: 451

Text #12

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.7604. Min Act: -0.1700

Data Index: 6062258 (Open Web Text)

Max Activating Token Index: 616

Text #13

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.7510. Min Act: -0.1700

Data Index: 4805112 (Open Web Text)

Max Activating Token Index: 900

Text #14

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.7839. Min Act: -0.1700

Data Index: 4129412 (Open Web Text)

Max Activating Token Index: 582

Text #15

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.7711. Min Act: -0.1700

Data Index: 3723984 (Open Web Text)

Max Activating Token Index: 1012

Text #16

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.7573. Min Act: -0.1700

Data Index: 5567017 (Open Web Text)

Max Activating Token Index: 909

Text #17

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.7671. Min Act: -0.1700

Data Index: 5298110 (Open Web Text)

Max Activating Token Index: 478

Text #18

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.7901. Min Act: -0.1700

Data Index: 2195141 (Open Web Text)

Max Activating Token Index: 780

Text #19

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.7789. Min Act: -0.1700

Data Index: 672156 (Open Web Text)

Max Activating Token Index: 211